© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 104629
    Prev
    Next
    INDEX
    Explanations

    just plug

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron is activating on content‐bearing tokens (nouns, verbs, adjectives, adverbs—i.e. “meaningful” words) and not on function words or punctuation.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ଂ
    -1.30
     πολι
    -1.27
     السياس
    -1.27
     делает
    -1.16
    对话框
    -1.16
     ofrecer
    -1.15
     pvp
    -1.13
     ayudar
    -1.13
     лекарства
    -1.13
     زيادة
    -1.13
    POSITIVE LOGITS
     your
    2.55
     you
    2.20
     yourself
    1.60
     will
    1.58
    如果你
    1.20
     متوسط
    1.19
     dann
    1.18
     here
    1.16
     You
    1.13
     вам
    1.13
    Activations Density 0.015%

    No Known Activations